Guidance Laws With Input Constraints and Actuator Failures

Liao, Fei; Ji, Haibo

doi:10.1002/asjc.1199

Cited by 10 publications

(5 citation statements)

References 19 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commonly seen model for the loss of effectiveness is that the actuator gain η decreases from η = 1 to a positive value less than one. And thus the actuator failure can be considered as follows [26]:…”

Section: Simulation Resultsmentioning

confidence: 99%

“…Standard model-based and model-free RL methods normally train a model or policy to be used at test time in advance based on assumption that actual environment match what they saw at training, however these is not the case and the change sometimes cause the controller to fail. When dealing with such changes like actuator failure and other perturbations in guidance problems, current guidance law normally consider such change as disturbance [26] or adjust guidance law parameters online [27]. These methods, however, limits its performance for not changing the nominal system.…”

Section: Meta-learningmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control

et al. 2019

View full text Add to dashboard Cite

In this paper, we present a novel guidance scheme based on model-based deep reinforcement learning (RL) technique. With model-based deep RL method, a deep neural network is trained as a predictive model of guidance dynamics which is incorporated into a model predictive path integral (MPPI) control framework. However, the traditional MPPI framework assumes the actual environment similar to the training dataset for the deep neural network which is impractical in practice with different maneuvering of the target, other perturbations, and actuator failures. To address this problem, our method utilizes meta-learning technique to make the deep neural dynamics model adapt to such changes online. With this approach, we can alleviate the performance deterioration of standard MPPI control caused by the difference between the actual environment and training data. Then, a novel guidance law for a varying velocity interceptor intercepting maneuvering target with desired terminal impact angle under actuator failure is constructed based on the aforementioned techniques. The simulation and experiment results under different cases show the effectiveness and robustness of the proposed guidance law in achieving successful interceptions of maneuvering target. INDEX TERMS Missile guidance, model predictive control, meta-learning, deep reinforcement learning, impact angle constraint.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Meta-learningmentioning

confidence: 99%

Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To tackle challenging environment and unknown highly variable dynamics, an adaptive guidance law and integrated navigation is proposed in [3] with deep meta-RL. Meta-learning can provide adaption to unforeseen environment changes through online learning while most traditional adaptive guidance is limited to specific faults [1] [14]. In Ref.…”

Section: A Deep Rl In Guidance Law Designmentioning

confidence: 99%

Range-Aware Impact Angle Guidance Law With Deep Reinforcement Meta-Learning

et al. 2020

View full text Add to dashboard Cite

In this paper, a new guidance law is proposed for impact angle constrained missile with timevarying velocity against a maneuvering target. The proposed guidance law is based on model-based deep reinforcement learning (RL) technique where a deep neural network is trained to be a predictive model used in model predictive path integral (MPPI) control. Tube-MPPI, a robust approach utilizing ancillary controller for disturbance rejection, is introduced in guidance law design in this work to deal with the MPPI degradation of robustness when the deep predictive model differs with actual environment. To further improve the performance, meta-learning is utilized to enable the deep neural dynamics adapt to environment changes online. With this approach the model mismatch of the nominal controller is reduced to improve tube-MPPI performance. Furthermore, a range-aware hyperbolic function is proposed as an adaptive function in the MPPI performance index design. Thus, reduced initial acceleration command and increased terminal velocity benefit guidance performance. Numerical simulations under various conditions demonstrate the effectiveness of proposed guidance law. INDEX TERMS Missile guidance, tube model predictive control, meta-learning, deep reinforcement learning, impact angle constraint

show abstract

“…In literature, 12 a back-stepping fault-tolerant guidance law was proposed by using the adaptive control to estimate the unknown effectiveness factor. In literature, 20 a three-dimensional fault-tolerant guidance law subjecting to actuator failures was proposed for interception of maneuvering targets. In literature, 21 based on the input-to-state stability, a novel three-dimensional fault-tolerant guidance law was designed for missile with actuator failure and external disturbances to intercept maneuvering target.…”

Section: Introductionmentioning

confidence: 99%

Fixed-time three-dimensional guidance law with input constraint and actuator faults

Liu

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

This paper investigates the three-dimensional guidance with the impact angle constraint, actuator faults and input constraint. Firstly, an adaptive three-dimensional guidance law with impact angle constraint is designed by using the terminal sliding mode control and nonhomogeneous disturbance observer. Then, in order to solve the problem of the input saturation and actuator faults, an adaptive anti-saturation fault-tolerant three-dimensional law is proposed by using the hyperbolic tangent function based on the passive fault-tolerant control. Finally, the effectiveness of the designed guidance laws is verified by using the Lyapunov function and simulation.

show abstract

Guidance Laws With Input Constraints and Actuator Failures

Cited by 10 publications

References 19 publications

Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control

Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control

Range-Aware Impact Angle Guidance Law With Deep Reinforcement Meta-Learning

Fixed-time three-dimensional guidance law with input constraint and actuator faults

Contact Info

Product

Resources

About